REVIEW 7 cited by
NeuralNDCG: Direct Optimisation of a Ranking Metric via Differentiable Relaxation of Sorting
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
NeuralNDCG: Direct Optimisation of a Ranking Metric via Differentiable Relaxation of Sorting
read the original abstract
Learning to Rank (LTR) algorithms are usually evaluated using Information Retrieval metrics like Normalised Discounted Cumulative Gain (NDCG) or Mean Average Precision. As these metrics rely on sorting predicted items' scores (and thus, on items' ranks), their derivatives are either undefined or zero everywhere. This makes them unsuitable for gradient-based optimisation, which is the usual method of learning appropriate scoring functions. Commonly used LTR loss functions are only loosely related to the evaluation metrics, causing a mismatch between the optimisation objective and the evaluation criterion. In this paper, we address this mismatch by proposing NeuralNDCG, a novel differentiable approximation to NDCG. Since NDCG relies on the non-differentiable sorting operator, we obtain NeuralNDCG by relaxing that operator using NeuralSort, a differentiable approximation of sorting. As a result, we obtain a new ranking loss function which is an arbitrarily accurate approximation to the evaluation metric, thus closing the gap between the training and the evaluation of LTR models. We introduce two variants of the proposed loss function. Finally, the empirical evaluation shows that our proposed method outperforms previous work aimed at direct optimisation of NDCG and is competitive with the state-of-the-art methods.
Forward citations
Cited by 7 Pith papers
-
Exposure-Based Reinforcement Learning to Rank
An exposure-based policy-gradient estimator for ranking is proposed; the appendix retracts the key derivation, and the reported experiments were not rerun with the corrected estimator.
-
SaFRO: Satisfaction-Aware Fusion via Dual-Relative Policy Optimization for Short-Video Search
A reinforcement-learning fusion framework using query reformulation, session gaps, and next-day retention as satisfaction rewards improved short-video search ranking and retention in Kuaishou's online A/B test.
-
Ranking Before Serving: Low-Latency LLM Serving via Pairwise Learning-to-Rank
A prompt-ranking scheduler that predicts relative output lengths with pairwise learning-to-rank and runs shorter LLM requests first reduces serving latency by up to 7.7x in burst tests.
-
LLM-Guided Semantic Relational Reasoning for Multimodal Intent Recognition
LGSRR uses LLM-generated semantic descriptions and rankings to improve multimodal intent recognition, reporting SOTA results on MIntRec2.0 and IEMOCAP-DA with gains around 0.5-1.3%.
-
Gradient-Boosted Decision Tree for Listwise Context Model in Multimodal Review Helpfulness Prediction
Introduces listwise attention, listwise loss, and GBDT predictor to improve multimodal review helpfulness ranking over prior FCNN and pairwise approaches.
-
Bringing GRACE to Recommendation: Fine-Tuning for Sustainable and Accurate Personalization
A fine-tuning framework uses soft sorting and gradient projection to make pretrained food recommenders greener without retraining or reranking.
-
SalesLoop: Reinforcement Learning from Performance Feedback for Sales Lead Ranking
A monthly closed-loop RL system for ranking sales leads, using position- and speed-weighted conversion rewards and a listwise GRPO-style loss, reports +7.9% NDCG@K offline and +4.7%/+8.7% conversion lift in a 160-day ...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.